© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16400
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names, especially the name "Shah"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inary
    -0.70
     bunny
    -0.70
     omn
    -0.69
    lear
    -0.67
     auxiliary
    -0.66
     gradient
    -0.65
     sentient
    -0.64
    VILLE
    -0.62
     fiber
    -0.62
    boro
    -0.61
    POSITIVE LOGITS
     Shah
    4.00
     Sharif
    1.68
     Hussain
    1.59
     Khan
    1.53
     Zah
    1.48
     Mohammad
    1.48
     Sultan
    1.46
     Shia
    1.41
     Sheikh
    1.41
     Ahmad
    1.38
    Activations Density 0.015%

    No Known Activations